Claims and customer contacts
Fraud and scam claims, and the customer calls, chats and emails that report them. Ready-to-run Grayson recipes with real responses, cost and latency.
| Recipe | Decides | Cost per 1,000 decisions | Latency (US-West) |
|---|---|---|---|
| Fraud typology classification | Label a fraud claim with a FraudClassifier class, scam type and contributing factors; decide reimbursement. | $0.53 to $0.71 | 249 to 288 ms |
| Triage customer calls, chats and messages for fraud reports | Find fraud reports and scams in progress among customer contacts; decide whether to freeze now and where to route. | $0.41 to $0.59 | 197 to 272 ms |
Each recipe has three examples with a realistic, detailed state: one with obvious fraud signals, one that is very likely legitimate, and one that is ambiguous. Cost is for those requests at $0.035 per million input tokens. Latency is the median of several calls of each through api.finic.ai from US-West; add your own network time from elsewhere.
See every category on the Recipes page.
Promotion abuse
Grayson decides whether a sign-up bonus or referral reward is being claimed through multiple accounts, a referral ring or staged deposits, and whether to pay it, hold it, deny it or close the account.
Contact triage
Grayson reads a call transcript, chat or secure message with the account's recent sign-ins, payments and contacts, and decides what it's about, whether to freeze now, where to route it and whether the customer is vulnerable.